---
title: "FairCognizer: A Model for Accurate Predictions with Inherent Fairness Evaluation (Extended Abstract)"
authors:
  - "Adda Akram Bendoukha"
  - "Nesrine Kaaniche"
  - "Aymen Boudguiga"
  - "Renaud Sirdey"
doi: "10.24963/ijcai.2025/1207"
url: "https://ijcai.org/proceedings/2025/1207"
pdf: "https://ijcai.org/proceedings/2025/1207.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10869-10874"
track: "Sister Conferences Best Papers"
keywords:
  - "Sister Conferences Best Papers: AI Ethics, Trust, Fairness"
---

# FairCognizer: A Model for Accurate Predictions with Inherent Fairness Evaluation (Extended Abstract)

Adda Akram Bendoukha, Nesrine Kaaniche, Aymen Boudguiga, Renaud Sirdey

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10869-10874. DOI: [10.24963/ijcai.2025/1207](https://doi.org/10.24963/ijcai.2025/1207)

## Abstract

Algorithmic fairness is a critical challenge in building trustworthy Machine Learning (ML)  models. ML classifiers strive to make predictions that closely match real-world observations (ground truth). However, if the ground truth data itself reflects biases against certain sub-populations, a dilemma arises: prioritize fairness and potentially reduce accuracy, or emphasize accuracy at the expense of fairness.
This work proposes a novel training framework that goes beyond achieving high accuracy. Our framework trains a classifier to not only deliver optimal predictions but also to identify potential fairness risks associated with each prediction. 
To do so, we specify a dual-labeling strategy where the second label contains a per-prediction fairness evaluation, referred to as an unfairness risk evaluation. In addition, we identify a subset of samples as highly vulnerable to group-unfair classifiers.
Our experiments demonstrate that our classifiers attain optimal accuracy levels on both the Adult-Census-Income and Compas-Recidivism datasets. Moreover, they identify unfair predictions with nearly 75% accuracy at the cost of expanding the size of the classifier by 45%.